© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21045
    Prev
    Next
    INDEX
    Explanations

    place names and locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    飽
    -0.11
    æĭīæĸ¯
    -0.10
     ØŃر
    -0.10
    ripp
    -0.10
     mav
    -0.09
    Öĥ
    -0.09
    Cow
    -0.09
     steril
    -0.09
    ingly
    -0.08
    ancell
    -0.08
    POSITIVE LOGITS
    çIJī
    0.09
     Dart
    0.09
    å»ī
    0.09
    ç®ķ
    0.09
    æī¶
    0.08
    çħ¤
    0.08
    .Gson
    0.08
     Toledo
    0.08
    éĴ¢éĵģ
    0.08
    涪
    0.08
    Activations Density 0.436%

    No Known Activations